Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific terms related to classification, guidelines, or categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "specific", "commercial", or "supplementary"

    np_acts-logits-general · gemini-2.0-flash

    qualifying specific terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     for
    -0.66
     in
    -0.63
     at
    -0.60
     to
    -0.58
     with
    -0.58
    ,
    -0.57
     as
    -0.57
     by
    -0.56
     on
    -0.56
     from
    -0.55
    POSITIVE LOGITS
     propOrder
    1.05
    RenderAtEndOf
    1.05
     autorytatywna
    1.03
     resourceCulture
    1.01
    GEBURTSDATUM
    0.99
    IndentedString
    0.97
    AddTagHelper
    0.97
     saites
    0.95
     typelib
    0.93
     المعيارى
    0.92
    Act Density 0.674%

    No Known Activations